The general critical analysis for continuous-time UPPAM recurrent neural networks

详细信息    查看全文

• 作者：Chen Qiao^a ; ^b ; ^{qiaochen@mail.xjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; ^{cqiao@tulane.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Wen-Feng Jing^a ; ^{wfjing@mail.xjtu.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Jian Fang^a ; ^b ; ^{jfang3@tulane.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yu-Ping Wang^b ; ^c ; ^{wyp@tulane.edu" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Continuous-time recurrent neural network ; Uniformly pseudo-projection-anti-monotone network ; General critical condition ; Dynamical analysis
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：29 January 2016
• 年：2016
• 卷：175
• 期：part_PA
• 页码：40-46
• 全文大小：507 K

文摘

The uniformly pseudo-projection-anti-monotone (UPPAM) neural network model, which can be considered as the unified continuous-time neural networks (CNNs), includes almost all of the known CNNs individuals. Recently, studies on the critical dynamic behaviors of CNNs have drawn special attentions due to its importance in both theory and applications. In this paper, we will present the analysis of the UPPAM network under the general critical conditions. It is shown that the UPPAM network possesses the global convergence and asymptotical stability under the general critical conditions if the network satisfies one quasi-symmetric requirement on the connective matrices, which is easy to be verified and applied. The general critical dynamics have rarely been studied before, and this work is an attempt to gain a meaningful assurance of general critical convergence and stability of CNNs. Since UPPAM network is the unified model for CNNs, the results obtained here can generalize and extend the existing critical conclusions for CNNs individuals, let alone those non-critical cases. Moreover, the easily verified conditions for general critical convergence and stability can further promote the applications of CNNs.